feat: Introduce pull-based cross-genome reference mechanism

README.md

@@ -955,18 +955,25 @@ Pages have a `last_updated` field in frontmatter. During lint passes:
 
 The agent proposes re-validation but does not change `maturity` without new source evidence.
 
-### Cross-genome lint
+### Cross-genome references
 
-A manual, monthly operation. Not automated in CI/CD — the token cost and coordination
+Cross-domain knowledge moves by **pull, never push**: the genome you are working in draws
-complexity are not justified at this scale.
+material _in_; nothing is ever written into another genome. There are **no cross-genome
+wikilinks** — submodule pointers make relative paths brittle.
 
-1. Operator initiates a master-repo agent session
+When the working genome needs a concept that lives elsewhere, the **navigation skill** handles
-2. Agent uses `qmd search "<concept>"` across the multi-genome index to find:
+it in the same two-phase shape as ingest:
-   - Concepts defined in 2+ genomes with potentially conflicting definitions
+
-   - Entities referenced cross-genome without canonical cross-genome wikilinks
+1. A deterministic collector clones the relevant genomes **read-only at HEAD** (fresh — never the
-   - Concepts in genome-X that should link to genome-Y
+   pinned submodule state) and assembles a dossier of excerpts with provenance.
-3. Agent reports findings — does not modify files
+2. A semantic pass reads only that dossier; the skill then deposits **one** abstract, non-private
-4. For each finding: create conflict note in the genome where resolution belongs
+   raw into the working genome at `raw/articles/crossgen-<topic>-<date>.md`.
+3. That raw goes through the working genome's normal ingest → PR → human gate, like any source.
+
+Which genomes may be read as **sources** is gated by a per-genome `cross_source: yes|no` flag: a
+confidential genome (e.g. a client file) is marked `no` and is never read as a source — the wall
+is structural, not a matter of the agent's discipline. The master `AGENTS.md` holds the full
+boundary contract.
 
 ---
 
@@ -1025,7 +1032,7 @@ and keep the wiki atomically navigable.
 ### Linking conventions
 
 - **Intra-genome:** `[[folder/file]]` — Obsidian wikilinks only.
-- **Cross-genome:** NOT supported via wikilink. Submodule pointers make relative paths brittle. When a concept belongs to another genome, use the navigation skill to emit a raw stub into that genome's `raw/articles/` directory so its local ingest pipeline can process it.
+- **Cross-genome:** NOT supported via wikilink — submodule pointers make relative paths brittle. When the working genome needs a concept that lives elsewhere, the navigation skill **pulls it in** as one abstract raw under _this_ genome's `raw/articles/`, which then goes through normal ingest. See [Cross-genome references](#cross-genome-references).
 - **External:** `[text](https://...)` — standard Markdown.
 
 ### Log format

lib/lint.sh

@@ -190,12 +190,21 @@ check_broken_links() {
   local links
   links=$(grep -oE '\[\[[^\]]+' "$file" 2>/dev/null | sed 's/^\[\[//' | cut -d'|' -f1)
 
-  for link in $links; do
+  # Cross-genome links (../other-genome/…) are not resolvable from a single
+  # genome checkout and are skipped — they would always fall
+  # through the two-level lookup and produce non-actionable warnings.
+  while IFS= read -r link; do
+    [[ -z "$link" ]] && continue
+
+    if [[ "$link" == ../* ]]; then
+      continue
+    fi
+
     local target="$link"
     [[ "$target" != *.md ]] && target="${target}.md"
 
     if [[ ! -f "${base_dir}/${target}" && ! -f "${base_dir}/../${target}" ]]; then
       warn "Potential broken link: [[$link]] in $file"
     fi
-  done
+  done <<< "$links"
 }